© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 2503
    Prev
    Next
    INDEX
    Explanations

    时

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    schild
    -0.08
     VAN
    -0.07
    ख
    -0.07
     Van
    -0.07
     Clifton
    -0.07
     lập
    -0.07
    ീറ്റ
    -0.07
    Kap
    -0.07
     weil
    -0.07
    crit
    -0.07
    POSITIVE LOGITS
     Plenty
    0.09
     auswählen
    0.08
     Wiz
    0.08
    hej
    0.08
     blends
    0.08
    arly
    0.08
     välja
    0.08
     Rabbi
    0.07
     nás
    0.07
     hum
    0.07
    Activations Density 0.002%

    No Known Activations